BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database
Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

Terminal-Bench Hard: Unspecified

Benchmark Family
Terminal-Bench Hard
Version or Variant
Unknown
Canonical Reference
terminal-bench-hard/default
Release Date
Unknown
Status
ACTIVE

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-013SM4-018 Mistral Small 4 Terminal-Bench Hard Overall 17.4% Unknown Primary source MSTRL-SM4
BR-014APLUS-002 Command A+ Terminal-Bench Hard Overall 25% Unknown Primary source COHR-APLUS
BR-014COMMANDA-006 Command A Terminal-Bench Hard Overall 0.8% Unknown Primary source COHR-COMMANDA
BR-014COMMANDAPLUS-007 Command A+ Terminal-Bench Hard Overall 25% Unknown Primary source COHR-APLUS
BR-014NORTHMINICODE-006 North Mini Code Terminal-Bench Hard Overall 31.1% Unknown Primary source COHR-NORTHMINICODE
BR-014TINYAYAGLOBAL-006 Tiny Aya Global Terminal-Bench Hard Overall 0% Unknown Primary source COHR-TINYAYAGLOBAL
BR-015LLAMA31NEMOTRONINSTRUCT70B-006 Llama 3.1 Nemotron Instruct 70B Terminal-Bench Hard Overall 4.5% Unknown Primary source NVDA-LLAMA31NEMOTRONINSTRUCT70B
BR-015LLAMA31NEMOTRONULTRA253BV1-006 Llama 3.1 Nemotron Ultra 253B v1 Terminal-Bench Hard Overall 2.3% Unknown Primary source NVDA-LLAMA31NEMOTRONULTRA253BV1
BR-015LLAMA33NEMOTRONSUPER49BV1-006 Llama 3.3 Nemotron Super 49B v1 Terminal-Bench Hard Overall 0% Unknown Primary source NVDA-LLAMA33NEMOTRONSUPER49BV1
BR-015LLAMA33NEMOTRONSUPER49BV1-016 Llama 3.3 Nemotron Super 49B v1 Terminal-Bench Hard Overall 0% Unknown Primary source NVDA-LLAMA33NEMOTRONSUPER49BV1
BR-015LLAMANEMOTRONSUPER49BV15-006 Llama Nemotron Super 49B v1.5 Terminal-Bench Hard Overall 3.8% Unknown Primary source NVDA-LLAMANEMOTRONSUPER49BV15
BR-015LLAMANEMOTRONSUPER49BV15-017 Llama Nemotron Super 49B v1.5 Terminal-Bench Hard Overall 5.3% Unknown Primary source NVDA-LLAMANEMOTRONSUPER49BV15
BR-015NEMOTRON3NANOOMNI30BA3BREASONING-006 Nemotron 3 Nano Omni 30B A3B Reasoning Terminal-Bench Hard Overall 8.3% Unknown Primary source NVDA-NEMOTRON3NANOOMNI30BA3BREASONING
BR-015NEMOTRON3ULTRA550BA55B-007 Nemotron 3 Ultra 550B A55B Terminal-Bench Hard Overall 36.4% Unknown Primary source NVDA-NEMOTRON3ULTRA550BA55B
BR-015NEMOTRONCASCADE230BA3B-006 Nemotron Cascade 2 30B A3B Terminal-Bench Hard Overall 21.2% Unknown Primary source NVDA-NEMOTRONCASCADE230BA3B
BR-015NVIDIANEMOTRON3NANO30BA3B-006 NVIDIA Nemotron 3 Nano 30B A3B Terminal-Bench Hard Overall 12.1% Unknown Primary source NVDA-NVIDIANEMOTRON3NANO30BA3B
BR-015NVIDIANEMOTRON3NANO30BA3B-019 NVIDIA Nemotron 3 Nano 30B A3B Terminal-Bench Hard Overall 13.6% Unknown Primary source NVDA-NVIDIANEMOTRON3NANO30BA3B
BR-015NVIDIANEMOTRON3NANO4B-007 NVIDIA Nemotron 3 Nano 4B Terminal-Bench Hard Overall 6.8% Unknown Primary source NVDA-NVIDIANEMOTRON3NANO4B
BR-015NVIDIANEMOTRON3SUPER120BA12B-007 NVIDIA Nemotron 3 Super 120B A12B Terminal-Bench Hard Overall 28.8% Unknown Primary source NVDA-NVIDIANEMOTRON3SUPER120BA12B
BR-015NVIDIANEMOTRONNANO12BV2VL-006 NVIDIA Nemotron Nano 12B v2 VL Terminal-Bench Hard Overall 4.5% Unknown Primary source NVDA-NVIDIANEMOTRONNANO12BV2VL
BR-015NVIDIANEMOTRONNANO12BV2VL-018 NVIDIA Nemotron Nano 12B v2 VL Terminal-Bench Hard Overall 0% Unknown Primary source NVDA-NVIDIANEMOTRONNANO12BV2VL
BR-015NVIDIANEMOTRONNANO9BV2-006 NVIDIA Nemotron Nano 9B V2 Terminal-Bench Hard Overall 0.8% Unknown Primary source NVDA-NVIDIANEMOTRONNANO9BV2
BR-015NVIDIANEMOTRONNANO9BV2-017 NVIDIA Nemotron Nano 9B V2 Terminal-Bench Hard Overall 1.5% Unknown Primary source NVDA-NVIDIANEMOTRONNANO9BV2
BR-016NOVA20LITE-007 Nova 2.0 Lite Terminal-Bench Hard Overall 16.7% Unknown Primary source AMZN-NOVA20LITE
BR-016NOVA20LITE-021 Nova 2.0 Lite Terminal-Bench Hard Overall 3.8% Unknown Primary source AMZN-NOVA20LITE
BR-016NOVA20LITE-033 Nova 2.0 Lite Terminal-Bench Hard Overall 6.8% Unknown Primary source AMZN-NOVA20LITE
BR-016NOVA20LITE-045 Nova 2.0 Lite Terminal-Bench Hard Overall 17.4% Unknown Primary source AMZN-NOVA20LITE
BR-016NOVA20OMNI-006 Nova 2.0 Omni Terminal-Bench Hard Overall 4.5% Unknown Primary source AMZN-NOVA20OMNI
BR-016NOVA20OMNI-018 Nova 2.0 Omni Terminal-Bench Hard Overall 6.8% Unknown Primary source AMZN-NOVA20OMNI
BR-016NOVA20OMNI-030 Nova 2.0 Omni Terminal-Bench Hard Overall 3.8% Unknown Primary source AMZN-NOVA20OMNI
BR-016NOVA20PROPREVIEW-007 Nova 2.0 Pro Preview Terminal-Bench Hard Overall 24.2% Unknown Primary source AMZN-NOVA20PROPREVIEW
BR-016NOVA20PROPREVIEW-022 Nova 2.0 Pro Preview Terminal-Bench Hard Overall 16.7% Unknown Primary source AMZN-NOVA20PROPREVIEW
BR-016NOVA20PROPREVIEW-036 Nova 2.0 Pro Preview Terminal-Bench Hard Overall 17.4% Unknown Primary source AMZN-NOVA20PROPREVIEW
BR-016NOVALITE-006 Nova Lite Terminal-Bench Hard Overall 0.8% Unknown Primary source AMZN-NOVALITE
BR-016NOVAMICRO-006 Nova Micro Terminal-Bench Hard Overall 1.5% Unknown Primary source AMZN-NOVAMICRO
BR-016NOVAPREMIER-006 Nova Premier Terminal-Bench Hard Overall 6.8% Unknown Primary source AMZN-NOVAPREMIER
BR-016NOVAPRO-006 Nova Pro Terminal-Bench Hard Overall 6.1% Unknown Primary source AMZN-NOVAPRO
BR-017GRANITE338B-006 Granite 3.3 8B Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE338B
BR-017GRANITE401B-006 Granite 4.0 1B Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE401B
BR-017GRANITE40350M-006 Granite 4.0 350M Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE40350M
BR-017GRANITE40H1B-006 Granite 4.0 H 1B Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE40H1B
BR-017GRANITE40H350M-006 Granite 4.0 H 350M Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE40H350M
BR-017GRANITE40HSMALL-006 Granite 4.0 H Small Terminal-Bench Hard Overall 2.3% Unknown Primary source IBM-GRANITE40HSMALL
BR-017GRANITE40MICRO-006 Granite 4.0 Micro Terminal-Bench Hard Overall 1.5% Unknown Primary source IBM-GRANITE40MICRO
BR-017GRANITE4130B-007 Granite 4.1 30B Terminal-Bench Hard Overall 2.3% Unknown Primary source IBM-GRANITE4130B
BR-017GRANITE413B-007 Granite 4.1 3B Terminal-Bench Hard Overall 2.3% Unknown Primary source IBM-GRANITE413B
BR-017GRANITE418B-007 Granite 4.1 8B Terminal-Bench Hard Overall 0% Unknown Primary source IBM-GRANITE418B
BR-018MOLMO28B-006 Molmo2-8B Terminal-Bench Hard Overall 0% Unknown Primary source AI2-MOLMO28B
BR-018MOLMO7BD-006 Molmo 7B-D Terminal-Bench Hard Overall 0% Unknown Primary source AI2-MOLMO7BD
BR-018OLMO232B-006 OLMo 2 32B Terminal-Bench Hard Overall 0% Unknown Primary source AI2-OLMO232B
BR-018OLMO27B-006 OLMo 2 7B Terminal-Bench Hard Overall 0% Unknown Primary source AI2-OLMO27B
BR-018OLMO3132BINSTRUCT-006 Olmo 3.1 32B Instruct Terminal-Bench Hard Overall 0% Unknown Primary source AI2-OLMO3132BINSTRUCT
BR-018OLMO3132BTHINK-006 Olmo 3.1 32B Think Terminal-Bench Hard Overall 0% Unknown Primary source AI2-OLMO3132BTHINK
BR-018OLMO332BTHINK-006 Olmo 3 32B Think Terminal-Bench Hard Overall 1.5% Unknown Primary source AI2-OLMO332BTHINK
BR-018OLMO37BINSTRUCT-006 Olmo 3 7B Instruct Terminal-Bench Hard Overall 0% Unknown Primary source AI2-OLMO37BINSTRUCT
BR-018OLMO37BTHINK-006 Olmo 3 7B Think Terminal-Bench Hard Overall 0.8% Unknown Primary source AI2-OLMO37BTHINK
BR-019MIMOV25-007 MiMo-V2.5 Terminal-Bench Hard Overall 41.7% Unknown Primary source XIAOM-MIMOV25
BR-019MIMOV25PRO-007 MiMo-V2.5-Pro Terminal-Bench Hard Overall 43.2% Unknown Primary source XIAOM-MIMOV25PRO
BR-019MIMOV25PRO-022 MiMo-V2.5-Pro Terminal-Bench Hard Overall 35.6% Unknown Primary source XIAOM-MIMOV25PRO
BR-019MIMOV2FLASH-007 MiMo-V2-Flash Terminal-Bench Hard Overall 25.8% Unknown Primary source XIAOM-MIMOV2FLASH
BR-019MIMOV2FLASH-020 MiMo-V2-Flash Terminal-Bench Hard Overall 28% Unknown Primary source XIAOM-MIMOV2FLASH
BR-019MIMOV2FLASHFEB2026-006 MiMo-V2-Flash (Feb 2026) Terminal-Bench Hard Overall 31.1% Unknown Primary source XIAOM-MIMOV2FLASHFEB2026
BR-019MIMOV2OMNI-006 MiMo-V2-Omni Terminal-Bench Hard Overall 34.8% Unknown Primary source XIAOM-MIMOV2OMNI
BR-019MIMOV2OMNI0327-006 MiMo-V2-Omni-0327 Terminal-Bench Hard Overall 35.6% Unknown Primary source XIAOM-MIMOV2OMNI0327
BR-019MIMOV2PRO-006 MiMo-V2-Pro Terminal-Bench Hard Overall 40.9% Unknown Primary source XIAOM-MIMOV2PRO
BR-020LFM212B-006 LFM2 1.2B Terminal-Bench Hard Overall 0% Unknown Primary source LQAI-LFM212B
BR-020LFM224BA2B-006 LFM2 24B A2B Terminal-Bench Hard Overall 0% Unknown Primary source LQAI-LFM224BA2B
BR-020LFM226B-006 LFM2 2.6B Terminal-Bench Hard Overall 0.8% Unknown Primary source LQAI-LFM226B
BR-020LFM2512BINSTRUCT-006 LFM2.5-1.2B-Instruct Terminal-Bench Hard Overall 0% Unknown Primary source LQAI-LFM2512BINSTRUCT
BR-020LFM2512BTHINKING-006 LFM2.5-1.2B-Thinking Terminal-Bench Hard Overall 0% Unknown Primary source LQAI-LFM2512BTHINKING
BR-020LFM258BA1B-006 LFM2.5-8B-A1B Terminal-Bench Hard Overall 4.5% Unknown Primary source LQAI-LFM258BA1B
BR-020LFM25VL16B-006 LFM2.5-VL-1.6B Terminal-Bench Hard Overall 0% Unknown Primary source LQAI-LFM25VL16B
BR-020LFM28BA1B-006 LFM2 8B A1B Terminal-Bench Hard Overall 0% Unknown Primary source LQAI-LFM28BA1B
BR-021LING1T-006 Ling-1T Terminal-Bench Hard Overall 10.6% Unknown Primary source INCAI-LING1T
BR-021LING261T-006 Ling-2.6-1T Terminal-Bench Hard Overall 31.1% Unknown Primary source INCAI-LING261T
BR-021LING26FLASH-007 Ling 2.6 Flash Terminal-Bench Hard Overall 21.2% Unknown Primary source INCAI-LING26FLASH
BR-021LINGFLASH20-006 Ling-flash-2.0 Terminal-Bench Hard Overall 10.6% Unknown Primary source INCAI-LINGFLASH20
BR-021LINGMINI20-006 Ling-mini-2.0 Terminal-Bench Hard Overall 0.8% Unknown Primary source INCAI-LINGMINI20
BR-021RING1T-006 Ring-1T Terminal-Bench Hard Overall 6.8% Unknown Primary source INCAI-RING1T
BR-021RING261T-007 Ring-2.6-1T Terminal-Bench Hard Overall 28.8% Unknown Primary source INCAI-RING261T
BR-021RINGFLASH20-006 Ring-flash-2.0 Terminal-Bench Hard Overall 7.6% Unknown Primary source INCAI-RINGFLASH20
BR-022EXAONE4012B-006 Exaone 4.0 1.2B Terminal-Bench Hard Overall 0% Unknown Primary source LGAI-EXAONE4012B
BR-022EXAONE4012B-017 Exaone 4.0 1.2B Terminal-Bench Hard Overall 0% Unknown Primary source LGAI-EXAONE4012B
BR-022EXAONE4032B-006 EXAONE 4.0 32B Terminal-Bench Hard Overall 1.5% Unknown Primary source LGAI-EXAONE4032B
BR-022EXAONE4032B-017 EXAONE 4.0 32B Terminal-Bench Hard Overall 3.8% Unknown Primary source LGAI-EXAONE4032B
BR-022EXAONE4533B-006 EXAONE 4.5 33B Terminal-Bench Hard Overall 20.5% Unknown Primary source LGAI-EXAONE4533B
BR-022KEXAONE-006 K-EXAONE Terminal-Bench Hard Overall 22.7% Unknown Primary source LGAI-KEXAONE
BR-022KEXAONE-017 K-EXAONE Terminal-Bench Hard Overall 6.8% Unknown Primary source LGAI-KEXAONE
BR-023HERMES4LLAMA31405B-006 Hermes 4 - Llama-3.1 405B Terminal-Bench Hard Overall 11.4% Unknown Primary source NOUS-HERMES4LLAMA31405B
BR-023HERMES4LLAMA31405B-017 Hermes 4 - Llama-3.1 405B Terminal-Bench Hard Overall 9.8% Unknown Primary source NOUS-HERMES4LLAMA31405B
BR-023HERMES4LLAMA3170B-006 Hermes 4 - Llama-3.1 70B Terminal-Bench Hard Overall 0% Unknown Primary source NOUS-HERMES4LLAMA3170B
BR-023HERMES4LLAMA3170B-017 Hermes 4 - Llama-3.1 70B Terminal-Bench Hard Overall 4.5% Unknown Primary source NOUS-HERMES4LLAMA3170B
BR-024SOLAROPEN100B-006 Solar Open 100B Terminal-Bench Hard Overall 2.3% Unknown Primary source UPSTG-SOLAROPEN100B
BR-024SOLARPRO2-006 Solar Pro 2 Terminal-Bench Hard Overall 4.5% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO2-017 Solar Pro 2 Terminal-Bench Hard Overall 3% Unknown Primary source UPSTG-SOLARPRO2
BR-024SOLARPRO3-007 Solar Pro 3 Terminal-Bench Hard Overall 7.6% Unknown Primary source UPSTG-SOLARPRO3
BR-025JAMBA17LARGE-006 Jamba 1.7 Large Terminal-Bench Hard Overall 2.3% Unknown Primary source AI21-JAMBA17LARGE
BR-025JAMBA17MINI-006 Jamba 1.7 Mini Terminal-Bench Hard Overall 0% Unknown Primary source AI21-JAMBA17MINI
BR-025JAMBAREASONING3B-006 Jamba Reasoning 3B Terminal-Bench Hard Overall 0.8% Unknown Primary source AI21-JAMBAREASONING3B
BR-026STEP35FLASH-006 Step 3.5 Flash Terminal-Bench Hard Overall 27.3% Unknown Primary source STPFN-STEP35FLASH